Model: GELU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1852 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.6473. Min Range: -5.6473

Max Act: 5.6473. Min Act: -0.1700

Data Index: 356785 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 5.6473. Min Range: -5.6473

Max Act: 5.5535. Min Act: -0.1700

Data Index: 709347 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 5.6473. Min Range: -5.6473

Max Act: 5.4910. Min Act: -0.1700

Data Index: 674764 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 5.6473. Min Range: -5.6473

Max Act: 5.4598. Min Act: -0.1695

Data Index: 752208 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 5.6473. Min Range: -5.6473

Max Act: 5.4598. Min Act: -0.1699

Data Index: 1280321 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 5.6473. Min Range: -5.6473

Max Act: 5.4598. Min Act: -0.1700

Data Index: 1284204 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 5.6473. Min Range: -5.6473

Max Act: 5.3973. Min Act: -0.1699

Data Index: 138910 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 5.6473. Min Range: -5.6473

Max Act: 5.3035. Min Act: -0.1700

Data Index: 1333325 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 5.6473. Min Range: -5.6473

Max Act: 5.3035. Min Act: -0.1699

Data Index: 1283920 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 5.6473. Min Range: -5.6473

Max Act: 5.2723. Min Act: -0.1700

Data Index: 1231168 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 5.6473. Min Range: -5.6473

Max Act: 5.2723. Min Act: -0.1700

Data Index: 843221 (C4 (Web Text))

Max Activating Token Index: 327

Text #11

Max Range: 5.6473. Min Range: -5.6473

Max Act: 5.2723. Min Act: -0.1700

Data Index: 1356114 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 5.6473. Min Range: -5.6473

Max Act: 5.1785. Min Act: -0.1700

Data Index: 961265 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 5.6473. Min Range: -5.6473

Max Act: 5.2098. Min Act: -0.1698

Data Index: 505609 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 5.6473. Min Range: -5.6473

Max Act: 5.1785. Min Act: -0.1700

Data Index: 909480 (C4 (Web Text))

Max Activating Token Index: 197

Text #15

Max Range: 5.6473. Min Range: -5.6473

Max Act: 5.1473. Min Act: -0.1700

Data Index: 1151601 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 5.6473. Min Range: -5.6473

Max Act: 5.1473. Min Act: -0.1700

Data Index: 925794 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 5.6473. Min Range: -5.6473

Max Act: 5.1160. Min Act: -0.1700

Data Index: 141260 (C4 (Web Text))

Max Activating Token Index: 306

Text #18

Max Range: 5.6473. Min Range: -5.6473

Max Act: 5.1473. Min Act: -0.1700

Data Index: 837186 (C4 (Web Text))

Max Activating Token Index: 883

Text #19

Max Range: 5.6473. Min Range: -5.6473

Max Act: 5.1160. Min Act: -0.1699

Data Index: 1244966 (C4 (Web Text))

Max Activating Token Index: 1011